Phase-based Method Research Articles

Robust arterial input function surrogate measurement from the superior sagittal sinus complex signal for fast dynamic contrast-enhanced MRI in the brain.

Accurately estimating the arterial input function for dynamic contrast-enhanced MRI is challenging. An arterial input function is typically determined from signal magnitude changes related to a contrast agent, often leading to underestimation of peak concentrations. Alternatively, signal phase recovers the accurate peak concentration for straight vessels but suffers from high noise. A recent method proposed to fit the signal in the complex plane by combining the advantages of the previous 2 methods. The purpose of this work is to refine this complex-based method to determine the venous output function (VOF), an arterial input function surrogate, from the superior sagittal sinus. We propose a state-of-the-art complex-based method that includes direct compensation for blood inflow and signal phase correction accounting for the curvature of the superior sagittal sinus, generally assumed collinear with B0 . We compared the magnitude-, phase-, and complex-based VOF determination methods against various simulated biases as well as for 29 brain metastases patients. Angulation of the superior sagittal sinus relative to B0 varied widely within patients, and its effect on the signal phase caused an underestimation of peak concentrations of up to 65%. Correction significantly increased the VOF peak concentration for the phase- and complex-based VOFs in the cohort. The phase-based method recovered accurate peak concentrations but lacked precision in the tail of the VOF. Our complex-based VOF completely recovered the effect of inflow and resulted in a high-peak concentration with limited noise. The new complex-based method resulted in high-quality VOF robust against superior sagittal sinus curvature and variations in patient positioning.

Motion correction for IRT imaging in neurosurgery: Analysis and comparison of frequency-/filter- and intensity-based approaches

In neurosurgery, the patient’s pulse and breathing motion, as well as technical and physiological artifacts during Infrared Thermography (IRT) acquisition cause difficulties; accordingly, a robust and adjusted motion correction method is required. In this paper, a comparison of frequency-/filter- and intensity-based approaches for the Horn-Schunck method, the Lucas-Kanade method, the OA-CLG method, the phase-based method, and FIR bandstop filter is provided. Firstly, images are registered with respect to a reference image, and image enhancement as a preprocessing step is carried out for those methods that rely on brightness constancy assumption (BCA) only. In the second step, motion estimation and compensation for local motion are applied to suppress small motion, i.e., pulse and breathing motion correction. The processing step can be done either with the frequency-/filter- or intensity-based approaches. Comparisons are performed using three types of datasets namely, the human IRT brain data (clinical cases), semi-synthetic IRT brain data, and phantom IRT data. Results from semi-synthetic and phantom IRT data indicate that the intensity-based methods are able to estimate and compensate pulse and breathing motion artifacts while preserving all the image details, structures, and spatial resolution after motion correction. The human brain datasets demonstrate that motion correction can be a beneficial step in IRT imaging during neurosurgery, obtaining better correction metric-wise in each four performance measurements.

A Quick Method of Phase Fitting in RF Segmented Demodulation

Ultrasound image of B-mode is reconstructed by DC(Direct Current) removal, quadrature demodulation, low-pass filtering, envelope detection and scanning conversion. Demodulation is the most important of the above. Because of the diversity of human organs and their corresponding acoustic properties, the shift frequency of echo signal changes as the depth increases. For a more accurate recovery signal, segmented function is used to describe the process. Traditionally, polynomial fitting or smooth spline was used to eliminate the discontinuity between the neighbor segment. In this brief, a phase-based quick-fitting method is proposed to optimize the step. Experimental investigation revealed that the phase fitting is applied to the linear array, and the mean-variance is 0.0002( MHz <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) compared with the smooth spline( 0.0033MHz <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ). For convex probe, the mean-variance( 0.0005MHz <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) is also smaller than that of polynomial fitting( 0.0046MHz <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ). Otherwise, this algorithm can overcome the boundary oscillation caused by frequency fitting. Especially, the results are stable even if the number of segments is large. Complex calculations are not required, the process can be implemented regardless of software and hardware.

Noncontact operational modal analysis of light poles by vision-based motion-magnification method

Light and sign poles on elevated highway bridge are secondary structural elements that support functionality of a highway system. Over the time, they may suffer from fatigue damage due to traffic, wind, and earthquake-induced vibration in a direct or indirect manner. As a secondary structural component, vibrations of light and sign poles are influenced by the bridge vibration, the primary structure. Structural condition assessment of the light and sign poles are normally conducted by visual inspection and/or vibration measurement using contact or noncontact method. In this paper, a vision-based vibration measurement of the light poles on elevated highway bridges using motion magnification and dynamic mode decomposition methods is proposed. Using the method, vibrations of the light poles are captured by video camera and the phase-based motion magnification method is implemented to magnify micro-vibration of the structure. By employing discretized centroid searching method, spatial displacements of the light poles are extracted. Modal parameters of the structure are then identified from the displacement responses by dynamic mode decomposition method. The study includes laboratory experiments for verification, and the full-scale implementation on existing light poles on elevated highway bridges. The vision-based results are compared with the noncontact vibration measurement using Laser-Doppler vibrometers. Results of experiments and full-scale tests demonstrate the capability of the proposed method in extracting multi-mode vibration characteristics of the light poles accurately in a noncontact long-distance measurement.

Experimental study of the effect of wind above irregular waves on the wave-induced load statistics

The design load from waves on offshore structures are often estimated by aid of experimental studies in wave flumes and basins. When going from open sea to laboratorial conditions a number of factors are either added or omitted such as wind above waves. The paddle-generated waves are based on a spectrum taking the indirect effect of wind into account, whereas the direct effect of wind is left out. Previous studies have focused on the direct effect of wind on waves themselves, but no investigations on the load have been made. The question is whether or not airflow separation, vortexes etc. in the wind field alter physical properties such as steepness of waves, the number of breaking waves and hereby the force; especially the in-line force. To investigate the matter, an experimental study of depth-integrated force on a circular cylinder from irregular waves both with and without wind above, was conducted. An objective, when conducting the tests, was to achieve the same significant wave height whether wind was present or not. Exceedance probability curves for wave crest height, depth-integrated force and pressure were obtained. Moreover, a more descriptive assessment of the phenomena was done by studying the average force shape of the hundred largest force events. In addition, there was applied a phase-based harmonic separation method to explore the wind's effect on the harmonic force components of higher order. The front steepness of the waves was clearly increased with the introduction of wind and further increased, when increasing the wind velocity. The introduction of wind consistently increased the number of breaking waves detected with a breaking criterion. The wave-induced load in the tail of the exceedance probability curve was only increased for some of the sea states, when wind was present. This was very dependent on the size of the crest height of the largest breaking waves. The maximum wave-induced pressure in the tail of the exceedance probability curve was on the contrary increased for all sea states, when wind was present, and it kept increasing with increasing wind velocity. For one of the sea states with increased force extrema, the averaged force shape for the hundred largest events of a case with wind revealed a shape with a spiky peak consistent with that generated from breaking waves. This was not present for the case without wind. The separated harmonic contents of the force up to fourth order also showed a tendency towards more energy at harmonic components of higher order for the case with wind.

A Phase-Based Ranging Method for Long-Range RFID Positioning With Quantum Tunneling Tags

This work demonstrates the ability to extend the positioning range of low-powered RFID tags to distances usually not achievable with other wireless or conventional RFID technologies. The technique is performed through a Received Signal Phase (RSP)-based method on a 5.8 GHz backscatter tunneling tag, in multipath-rich indoor and outdoor environments, at distances up to 35 meters from the reader. Distance errors as low as 0.1% of the total reader-to-tag distance were observed with average errors of 0.8% and 0.6% for indoor and outdoor environments, respectively. Compared to Received Signal Strength (RSS)-based techniques, the average distance estimation accuracy is improved by a factor of 51 and 38 for indoor and outdoor environments, respectively. Moreover, an Effective Isotropic Radiated Power (EIRP) of only 10.5 dBm and a biasing power for the tunneling tag of only $21.3~\mu \text{W}$ at 80 mV promise a low-power, long-range sub-meter scale positioning technique with a projected maximum range over 1 km.

Dynamics and phase-based vibration suppression of rotating flexible shaft with unstressed initial deformation under several parametric excitations

A rotating flexible cantilever shaft is modeled with unstressed initial deformation under several parametric excitations, including fluctuant speed, axial force, torque and nonlinear radial follower force. Its dynamics is calculated via an improved Hill's method which is suitable for harmonic processing. An iteration method for solving the steady-state response of the nonlinear system's dynamics is proposed, and the stability is determined by the perturbation of the steady-state response. Considering the effects of a single excitation and different excitations’ coupling, two criteria for evaluating the system's dynamics are investigated by numerical simulation. One is the eccentric degree of the shaft's rotating deformation, and the other is the stability of the shaft system. The excitations’ coupling effect provides a novel method, called the phase-based vibration suppression method in this paper, to suppress the rotating deformation of a shaft with fluctuant speed or radial follower force by applying an extra fluctuant axial force or torque. Meanwhile, this systematic method to solve the steady-state dynamics of the shaft is universal for practical engineering.

Extracting full-field subpixel structural displacements from videos via deep learning

Conventional displacement sensing techniques (e.g., laser, linear variable differential transformer) have been widely used in structural health monitoring in the past two decades. Though these techniques are capable of measuring displacement time histories with high accuracy, distinct shortcoming remains such as point-to-point contact sensing which limits its applicability in real-world problems. Video cameras have been widely used in the past years due to advantages that include low price, agility, high spatial sensing resolution, and non-contact. Compared with target tracking approaches (e.g., digital image correlation, template matching, etc.), the phase-based method is powerful for detecting small subpixel motions without the use of paints or markers on the structure surface. Nevertheless, the complex computational procedure limits its real-time inference capacity. To address this fundamental issue, we develop a deep learning framework based on convolutional neural networks (CNNs) that enable real-time extraction of full-field subpixel structural displacements from videos. In particular, two new CNN architectures are designed and trained on a dataset generated by the phase-based motion extraction method from a single lab-recorded high-speed video of a dynamic structure. As displacement is only reliable in the regions with sufficient texture contrast, the sparsity of motion field induced by the texture mask is considered via the network architecture design and loss function definition. Results show that, with the supervision of full and sparse motion field, the trained network is capable of identifying the pixels with sufficient texture contrast as well as their subpixel motions. The performance of the trained networks is tested on various videos of other structures to extract the full-field motion (e.g., displacement time histories), which indicates that the trained networks have generalizability to accurately extract full-field subpixel displacements for pixels with sufficient texture contrast.

Implementation of video motion magnification technique for non-contact operational modal analysis of light poles

Damages on lights and utility poles mounted on the elevated highway or railway bridges were observed in the past several large earthquakes. The damages could have serious consequences to public safety, travelling vehicles or trains, and nearby properties. A previous study shows that the damages were caused by buckling and yielding of the pole due to excessive response amplification during large earthquake. Such amplification occurs when the bridge's natural frequency is close to the light pole's fundamental frequency. An investigation of the seismic performance of existing light pole mounted on elevated highway bridges is needed to avoid the response amplification. This includes the identification of the light pole's natural frequency and damping ratio. Vibration testing of the light pole using conventional contact sensors individually would require enormous effort and is time-consuming. Moreover, such vibration testing on a highway bridge deck would require traffic disruption to provide access. Video camera-based non-contact vision sensing is seen as a promising alternative to the conventional contact sensors for this purpose. The objective of this paper is to explore the use of non-contact vision sensing for operational modal analysis of light pole on highway viaduct. The phase-based video motion magnification method is implemented to obtain the light pole response in an ambient condition. Using this method, small and invisible displacement is magnified for a certain range of frequency of interest. Based on the magnified video frames, structural displacement is extracted using the image processing technique. The natural frequency and damping ratio of the light pole are estimated using the random decrement technique. The method is verified in a laboratory-scale experiment and implemented to practical field measurements of a light pole on a highway viaduct in Kanagawa, Japan. The results are compared with measurement by Laser Doppler Vibrometer. Both experiments suggest that the method could effectively obtain the natural frequency and damping ratio of the structures under the ambient condition where vibration amplitudes are very small and invisible with reasonable accuracy.

Chest X-ray image phase features for improved diagnosis of COVID-19 using convolutional neural network.

Purpose:Recently, the outbreak of the novel coronavirus disease 2019 (COVID-19) pandemic has seriously endangered human health and life. In fighting against COVID-19, effective diagnosis of infected patient is critical for preventing the spread of diseases. Due to limited availability of test kits, the need for auxiliary diagnostic approach has increased. Recent research has shown radiography of COVID-19 patient, such as CT and X-ray, contains salient information about the COVID-19 virus and could be used as an alternative diagnosis method. Chest X-ray (CXR) due to its faster imaging time, wide availability, low cost, and portability gains much attention and becomes very promising. In order to reduce intra- and inter-observer variability, during radiological assessment, computer-aided diagnostic tools have been used in order to supplement medical decision making and subsequent management. Computational methods with high accuracy and robustness are required for rapid triaging of patients and aiding radiologist in the interpretation of the collected data. Method:In this study, we design a novel multi-feature convolutional neural network (CNN) architecture for multi-class improved classification of COVID-19 from CXR images. CXR images are enhanced using a local phase-based image enhancement method. The enhanced images, together with the original CXR data, are used as an input to our proposed CNN architecture. Using ablation studies, we show the effectiveness of the enhanced images in improving the diagnostic accuracy. We provide quantitative evaluation on two datasets and qualitative results for visual inspection. Quantitative evaluation is performed on data consisting of 8851 normal (healthy), 6045 pneumonia, and 3323 COVID-19 CXR scans. Results:In Dataset-1, our model achieves 95.57% average accuracy for a three classes classification, 99% precision, recall, and F1-scores for COVID-19 cases. For Dataset-2, we have obtained 94.44% average accuracy, and 95% precision, recall, and F1-scores for detection of COVID-19.Conclusions:Our proposed multi-feature-guided CNN achieves improved results compared to single-feature CNN proving the importance of the local phase-based CXR image enhancement. Future work will involve further evaluation of the proposed method on a larger-size COVID-19 dataset as they become available.

Manifestation of Flexural Vibration Modes of Rails by the Phase-Based Magnification Method

With the recent development of high performance photography devices, vibration measurements using digital image processing can be utilized for the condition monitoring and the analysis of generation mechanisms. High-quality image recording provides very dense spatial information unlike physical sensors with a limited number of point-oriented measurements and output channels such as accelerometers. Moreover, image acquisition is a non-contact technique and ensures that the installed sensors do not affect the mass or stiffness. In this study, the vibration mode of rails is investigated using the phase-based video magnification method. An extensive amount of information that cannot be detected by human eyes, can be obtained with this imaging motion magnification technique by amplifying and visualising the minute vibrational movements. Flexural vibration modes in rails generate rolling noise, especially at high frequencies where the displacement amplitudes are small. The motion magnification method is applied using a high-speed camera to measure the rail mode shapes. The measured mode shapes are compared to the numerical results obtained from the waveguide finite element method. This method helps in understanding the vibration generation and the transfer mechanisms in the waveguide structures with a uniform cross-section in the lengthwise direction such as a railway track.

Carrier Phase-Based Ionospheric Gradient Monitor Under the Mixed Gaussian Distribution

Anomalous ionospheric gradient is a critical risk to be monitored by ground-based augmentation systems (GBASs) utilized for safety-of-life navigation applications. A dual-frequency carrier phase-based ionospheric gradient monitoring method is proposed under the mixed Gaussian distribution. The minimum detection error of the proposed method can be greatly reduced by allowing acceptable ambiguity resolution failure modes, given the required averaging length. The real BeiDou navigation satellite system data were utilized to test the proposed method. The experimental results showed that the minimum detection error (MDE) of the proposed dual-frequency ionospheric gradient monitoring method can be reduced by at least 30% in comparison with the maximum acceptable anomalous ionospheric gradient of category III GBAS. This study demonstrated that the proposed method can be used to protect against the ionospheric gradient for a ground-based augmentation system.

Kidney Segmentation in 3-D Ultrasound Images Using a Fast Phase-Based Approach.

Renal ultrasound (US) imaging is the primary imaging modality for the assessment of the kidney's condition and is essential for diagnosis, treatment and surgical intervention planning, and follow-up. In this regard, kidney delineation in 3-D US images represents a relevant and challenging task in clinical practice. In this article, a novel framework is proposed to accurately segment the kidney in 3-D US images. The proposed framework can be divided into two stages: 1) initialization of the segmentation method and 2) kidney segmentation. Within the initialization stage, a phase-based feature detection method is used to detect edge points at kidney boundaries, from which the segmentation is automatically initialized. In the segmentation stage, the B-spline explicit active surface framework is adapted to obtain the final kidney contour. Here, a novel hybrid energy functional that combines localized region- and edge-based terms is used during segmentation. For the edge term, a fast-signed phase-based detection approach is applied. The proposed framework was validated in two distinct data sets: 1) 15 3-D challenging poor-quality US images used for experimental development, parameters assessment, and evaluation and 2) 42 3-D US images (both healthy and pathologic kidneys) used to unbiasedly assess its accuracy. Overall, the proposed method achieved a Dice overlap around 81% and an average point-to-surface error of ~2.8 mm. These results demonstrate the potential of the proposed method for clinical usage.

Experimental and numerical study of free-surface wave resonance in the gap between two elongated parallel boxes with square corners

Experiments with wave groups are carried out to investigate 3D wave resonance in the gap between two fixed parallel elongated boxes with square corners. The gap responses are re-created in a numerical wave tank using computational fluid dynamics (CFD) with reasonable accuracy. Based on the CFD results with high temporal and spatial resolution, the free-surface behaviour, internal flow velocity and vortex structures near the gap are interrogated in detail to gain insights into the behaviour. It is found that the damping which affects the oscillatory motion in the gap appears to be linear (or at least dominated by linear damping) except for the largest excitation, though substantial flow separation is present. A phase-based harmonic separation method is used to extract the harmonics of the wave field, which is found useful in understanding the dynamics of wave-structure interactions for gap resonance problems.

Local Riesz Pyramid for Faster Phase-Based Video Magnification

Phase-based video magnification methods can magnify and reveal subtle motion changes invisible to the naked eye. In these methods, each image frame in a video is decomposed into an image pyramid, and subtle motion changes are then detected as local phase changes with arbitrary orientations at each pixel and each pyramid level. One problem with this process is a long computational time to calculate the local phase changes, which makes high-speed processing of video magnification difficult. Recently, a decomposition technique called the Riesz pyramid has been proposed that detects only local phase changes in the dominant orientation. This technique can remove the arbitrariness of orientations and lower the over-completeness, thus achieving high-speed processing. However, as the resolution of input video increases, a large amount of data must be processed, requiring a long computational time. In this paper, we focus on the correlation of local phase changes between adjacent pyramid levels and present a novel decomposition technique called the local Riesz pyramid that enables faster phase-based video magnification by automatically processing the minimum number of sufficient local image areas at several pyramid levels. Through this minimum pyramid processing, our proposed phase-based video magnification method using the local Riesz pyramid achieves good magnification results within a short computational time.

Accurate detection of lameness in dairy cattle with computer vision: A new and individualized detection strategy based on the analysis of the supporting phase

Lameness has a considerable influence on the welfare and health of dairy cows. Many attempts have been made to develop automatic lameness detection systems using computer vision technology. However, these detection methods are easily affected by the characteristics of individual cows, resulting in inaccurate detection of lameness. Therefore, this study explores an individualized lameness detection method for dairy cattle based on the supporting phase using computer vision. This approach is applied to eliminate the influence of the characteristics of individual cows and to detect lame cows and lame hooves. In this paper, the correlation coefficient between lameness and the supporting phase is calculated, a lameness detection algorithm based on the supporting phase is proposed, and the accuracy of the algorithm is verified. Additionally, the reliability of this method using computer vision technology is verified based on deep learning. One hundred naturally walking cows are selected from video data for analysis. The results show that the correlation between lameness and the supporting phase was 0.864; 96% of cows were correctly classified, and 93% of lame hooves were correctly detected using the supporting phase-based lameness detection algorithm. The mean average precision is 87.0%, and the number of frames per second is 83.3 when the Receptive Field Block Net Single Shot Detector deep learning network was used to detect the locations of cow hooves in the video. The results show that the supporting phase-based lameness detection method proposed in this paper can be used for the detection and classification of cow lameness and the detection of lame hooves with high accuracy. This approach eliminates the influence of individual cow characteristics and could be integrated into an automatic detection system and widely applied for the detection of cow lameness.

Identification of full-field dynamic modes using continuous displacement response estimated from vibrating edge video

The video of vibrating structure provides dense quantitative continuous spatial information that is harnessed using various computer vision algorithms in the past decade. Computer vision algorithms that implement sparse optical flow, have been successful in acquiring the Lagrangian representation of motion. Such vision-based measurement already proved its potential in replacing the need for a contact based vibration measurement sensors. In order to obtain full-field, spatially dense, vibrational modes, a large number of discrete sensors would be necessary throughout the specimen’s length, making it impractical. The phase-based video processing method is found to be successful in visualizing full-field operational mode shapes of a vibrating structure. However, the phase-based optical flow provides an Eulerian representation of the motion at every pixel of the image space, which does not acquire the full-field spatiotemporal Lagrangian displacement trajectory of the structure. Hence, there is a need to design a target-free, noncontact vision-based framework that can directly extract and quantify full-field dynamic modes of a real-life vibrating structural member from its video, by acquiring the trajectory of every particle on the structure at each frame of the video using optical flow. The continuous edge of a moving object is a rich optical feature whose motion perpendicular to its orientation can be tracked in Lagrangian coordinates using optical flow. In a recent paper by authors, the method of measuring full-field displacement response of a vibrating continuous edge of a structural member has been reported. In this paper, the full-field displacement response is acquired using the recently presented method and subsequently, its spatially dense dynamic modes are extracted from its video using the acquired full-field spatiotemporal displacement response of the vibrating structure. The full-field dynamic modes and modal parameters are extracted using the Hankel dynamic mode decomposition method, which is applicable both for linear, as well as nonlinear dynamical systems. Further, experimental validation of the proposed method is presented for two kinds of structures (1) a three-story steel frame, and (2) an aluminum cantilever beam, both undergoing free vibration. The results obtained using the proposed method is validated with the displacement measured using Laser Doppler Vibrometer at a particular point of the edge. The extracted modal properties using the proposed methodology compares satisfactorily with the results of the eigensystem realization algorithm applied to the discrete point accelerometer measurements attached at all three floors of the frame. Also, the numerically obtained mode shapes from the analytical model of the cantilever beam validate the estimated modal parameters and the full-field mode shapes. To validate the efficacy of the proposed method in real-world structures, part of the vibrating cable of Tacoma Narrows bridge is tracked from its video, moments before its collapse. The proposed method does successfully extract the dominating vibrational modes of the cables of the Tacoma Narrows bridge.

The pruning phenological phase-based method for extracting tea plantations by field hyperspectral data and Landsat time series imagery

Tea plantations expansion has occurred in the major tea planting area of Yunnan province, China, however, it is a big challenge to extract and map the distribution of tea plantations due to their non-obvious phenological characteristics in the tropical and subtropical regions. Firstly, we demonstrated the pruning phenological phase of tea plantations by using field hyperspectral data. Secondly, we analyzed the optical features of typical land cover types from the available time series Landsat imagery with the Google Earth Engine (GEE) platform. We proposed a pixel and phenology- based approach to extract and map tea plantations distribution at the 30-m resolution of the historical time period of 2015 to 2019. The resultant map had high user/producer accuracies of 91.07% and 86.90%, respectively. Our study provides a promising new approach to extract and map tea plantations in complex tropical landscapes at fine spatial resolution by using only free historical Landsat imagery.

Video super-resolution with phase-aided deformable alignment network

Video super-resolution (VSR) aims to restore a high-resolution frame from its corresponding reference frame and a series of neighboring frames in low resolution. Because of the displacement between the reference frame and each neighboring frame, which is caused by the motion of the camera or observed objects, VSR methods usually initially align the neighboring frames with the reference frame. However, the commonly used motion estimation and compensation methods highly depend on the predicted optical flow and they are affected by the lighting change. We propose a phase-aided deformable alignment network (PDAN) to alleviate the above problems. In PDAN, a phase-based method is introduced in the motion estimation subnetwork along with the traditional U-Net structure, which improves the restoration robustness in scenarios of lighting change. A deformable convolutional network is further adopted in the alignment subnetwork to enhance the alignment for objects with an irregular shape and motion distortion, which also avoids the dependence on explicit motion representation accuracy. Moreover, the reconstruction module is optimized for improved restoration. Extensive experiments conducted demonstrate that PDAN achieves state-of-the-art quantitative and qualitative performances.

Camera-Based Micro-Vibration Measurement for Lightweight Structure Using an Improved Phase-Based Motion Extraction

Video cameras are capable to collect high-density spatial data as each pixel is a sensor. An issue is that the video data is difficult to convert into the motion information, such as displacement. This paper presents a novel camera-based vibration measurement methodology for the lightweight structure. First, the phase-based motion extraction method is improved by directly transforming the phase variations into the displacement without the computation of phase gradient. The displacement is then converted into acceleration information to describe the vibration. Moreover, the proposed vibration measurement is investigated for a lightweight structure without attached sensors to change the physical properties. The measurements of the acceleration signals from camera and accelerometer are compared for verification. The experimental results for the effect of mass-loading, different camera parameters and down-sampling on the measurement validate the effectiveness of the proposed method.